Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Prepare external memory support for hist. (#7638)

Browse Source 
This PR prepares the GHistIndexMatrix to host the column matrix which is used by the hist tree method by accepting sparse_threshold parameter.

Some cleanups are made to ensure the correct batch param is being passed into DMatrix along with some additional tests for correctness of SimpleDMatrix.
This commit is contained in:
Jiaming Yuan
2022-02-10 16:58:02 +08:00
committed by GitHub
parent 87c01f49d8
commit 2775c2a1ab
24 changed files with 368 additions and 201 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
src/data/simple_dmatrix.cc
View File

@@ -74,12 +74,18 @@ BatchSet<SortedCSCPage> SimpleDMatrix::GetSortedColumnBatches() {
return BatchSet<SortedCSCPage>(begin_iter);
}
namespace {
void CheckEmpty(BatchParam const& l, BatchParam const& r) {
if (l == BatchParam{}) {
CHECK(r != BatchParam{}) << "Batch parameter is not initialized.";
}
}
} // anonymous namespace
BatchSet<EllpackPage> SimpleDMatrix::GetEllpackBatches(const BatchParam& param) {
// ELLPACK page doesn't exist, generate it
if (!(batch_param_ != BatchParam{})) {
CHECK(param != BatchParam{}) << "Batch parameter is not initialized.";
}
if (!ellpack_page_ || (batch_param_ != param && param != BatchParam{})) {
CheckEmpty(batch_param_, param);
if (!ellpack_page_ || RegenGHist(batch_param_, param)) {
CHECK_GE(param.gpu_id, 0);
CHECK_GE(param.max_bin, 2);
ellpack_page_.reset(new EllpackPage(this, param));
@@ -91,17 +97,15 @@ BatchSet<EllpackPage> SimpleDMatrix::GetEllpackBatches(const BatchParam& param)
}
BatchSet<GHistIndexMatrix> SimpleDMatrix::GetGradientIndex(const BatchParam& param) {
if (!(batch_param_ != BatchParam{})) {
CHECK(param != BatchParam{}) << "Batch parameter is not initialized.";
}
CheckEmpty(batch_param_, param);
if (!gradient_index_ || RegenGHist(batch_param_, param)) {
LOG(INFO) << "Generating new Gradient Index.";
CHECK_GE(param.max_bin, 2);
CHECK_EQ(param.gpu_id, -1);
// Used only by approx.
auto sorted_sketch = param.regen;
gradient_index_.reset(
new GHistIndexMatrix(this, param.max_bin, sorted_sketch, this->ctx_.Threads(), param.hess));
gradient_index_.reset(new GHistIndexMatrix(this, param.max_bin, param.sparse_thresh,
sorted_sketch, this->ctx_.Threads(), param.hess));
batch_param_ = param;
CHECK_EQ(batch_param_.hess.data(), param.hess.data());
}